Triple
T19551635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Invisible Touch |
E489209
|
entity |
| Predicate | hasNotableUSNumberOne |
P136556
|
FINISHED |
| Object | true |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: true | Statement: [Invisible Touch, hasNotableUSNumberOne, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNotableUSNumberOne Context triple: [Invisible Touch, hasNotableUSNumberOne, true]
-
A.
hasBillboard200NumberOne
Indicates that an entity (typically an album or song) has reached the number one position on the Billboard 200 chart.
-
B.
numberOfUSNumberOneSingles
Indicates the count of times an entity has achieved a number-one single on the official United States music charts.
-
C.
hasNotableSongNumber
Indicates that an entity is associated with a specific song identified by its notable number or index within a collection or sequence.
-
D.
achievedNumberOneInCountry
Indicates that an entity reached the number one position in a ranking, chart, or listing within a specified country.
-
E.
hasBillboardCountryNumberOneSingle
Indicates that an entity has achieved at least one single that reached number one on the Billboard Country music charts.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e8dc5d8c8190a6d7bd8864f43ca0 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63d30a1d8819084d1bc60a5e49cae |
completed | April 20, 2026, 2:50 p.m. |
| PD | Predicate disambiguation | batch_69e514d4df3c8190b7e9b3b4fdf9452a |
completed | April 19, 2026, 5:45 p.m. |
| PDg | Predicate description generation | batch_69e51796b4c48190b721114dde654bd7 |
completed | April 19, 2026, 5:57 p.m. |
Created at: April 10, 2026, 1:41 p.m.